Systems and methods for automatic formatting of images for media assets based on user profile
Systems and methods are provided herein for personalizing images that correspond to a media asset identifier by using user profile information. As an example, the television series “Community” has several actors, such as Joel McHale, Chevy Chase, and Ken Jeong. Poster art developed by an editor o50533238_1f “Community” may include an image that portrays each of Joel McHale, Chevy Chase, and Ken Jeong. In order to personalize the image, control circuitry may determine which actor(s) the user prefers, and crop out only those actors in the poster art to create a personalized image. As an example, if the user prefers Joel McHale, control circuitry may crop out the portrayal of Joel McHale and use only that portion of the image to display next to other text describing “Community.”
1. A method for selectively generating for display portions of an image based on a user profile, the method comprising:
identifying an image corresponding to a requested media asset, wherein the image comprises a plurality of portions, and wherein each portion of the plurality of portions comprises a respective depiction of a person;
determining an identity of each respective person in each respective portion of the plurality of portions;
generating an affinity ranking for each respective person based on a user profile;
identifying each combination of two or more of the portions of the image to generate a plurality of subsets of portions of the image;
calculating a combined affinity ranking for each respective subset based on the affinity ranking of each person depicted by the respective subset;
identifying a preferred subset with a highest combined affinity ranking;
determining whether the preferred subset comprises two non-adjacent portions of the plurality of portions;
in response to determining that the preferred subset comprises two non-adjacent portions of the plurality of portions:
cropping out each of the two non-adjacent portions; and
stitching the cropped non-adjacent portions together to generate a stitched image; and
generating for display, the stitched image.
2. The method of claim 1 , wherein determining the identity of each respective person depicted in each respective portion of the plurality of portions comprises performing facial recognition on each respective depiction of a person of the image.
3. The method of claim 1 , further comprising:
recognizing textual content in the image; and
generating for simultaneous display the textual content with the subset with the highest combined affinity ranking.
4. The method of claim 1 , further comprising:
determining characteristics of the subset with the highest combined affinity ranking;
determining, based on the characteristics of the subset with the highest combined affinity ranking, optimal characteristics for features surrounding the subset with the highest combined affinity ranking in the respective portion; and
altering characteristics of the features surrounding the subset with the highest combined affinity ranking to reflect the optimal characteristics.
5. A system for selectively generating for display portions of an image based on a user profile, the system comprising:
control circuitry configured to:
identify an image corresponding to a requested media asset, wherein the image comprises a plurality of portions, and wherein each portion of the plurality of portions comprises a respective depiction of a person;
determine an identity of each respective person in each respective portion of the plurality of portions;
generate an affinity ranking for each respective person based on a user profile;
identify each combination of two or more of the portions of the image to generate a plurality of subsets of portions of the image;
calculate a combined affinity ranking for each respective subset based on the affinity ranking of each person depicted by the respective subset;
identify a preferred subset with a highest combined affinity ranking;
determine whether the preferred subset comprises two non-adjacent portions of the plurality of portions;
in response to determining that the preferred subset comprises two non-adjacent portions of the plurality of portions:
crop out each of the two non-adjacent portions; and
stitch the cropped non-adjacent portions together to generate a stitched image; and
generate for display, the stitched image.
6. The system of claim 5 , wherein determining the identity of each respective person depicted in each respective portion of the plurality of portions comprises performing facial recognition on each respective depiction of a person of the image.
7. The method of claim 5 , further comprising:
recognizing textual content in the image; and
generating for simultaneous display the textual content with the subset with the highest combined affinity ranking.
8. The method of claim 5 , further comprising:
determining characteristics of the subset with the highest combined affinity ranking;
determining, based on the characteristics of the subset with the highest combined affinity ranking, optimal characteristics for features surrounding the subset with the highest combined affinity ranking in the respective portion; and
altering characteristics of the features surrounding the subset with the highest combined affinity ranking to reflect the optimal characteristics.
9. A non-transitory computer readable medium having instructions encoded thereon, that when executed by control circuitry causes the control circuitry to:
identify an image corresponding to a requested media asset, wherein the image comprises a plurality of portions, and wherein each portion of the plurality of portions comprises a respective depiction of a person;
determine an identity of each respective person in each respective portion of the plurality of portions;
generate an affinity ranking for each respective person based on a user profile;
identify each combination of two or more of the portions of the image to generate a plurality of subsets of portions of the image;
calculate a combined affinity ranking for each respective subset based on the affinity ranking of each person depicted by the respective subset;
identify a preferred subset with a highest combined affinity ranking;
determine whether the preferred subset comprises two non-adjacent portions of the plurality of portions; and
in response to determining that the preferred subset comprises two non-adjacent portions of the plurality of portions:
crop out each of the two non-adjacent portions; and
stitch the cropped non-adjacent portions together to generate a stitched image; and
generate for display, the stitched image.
10. The non-transitory computer-readable medium of claim 9 , wherein, wherein determining the identity of each respective person depicted in each respective portion of the plurality of portions comprises performing facial recognition on each respective depiction of a person of the image.
11. The non-transitory computer-readable medium of claim 9 , wherein the instructions further comprise:
recognizing textual content in the image; and
generating for simultaneous display the textual content with the subset with the highest combined affinity ranking.
12. The non-transitory computer-readable medium of claim 9 , wherein the instructions further comprise:
determining characteristics of the subset with the highest combined affinity ranking;
determining, based on the characteristics of the subset with the highest combined affinity ranking, optimal characteristics for features surrounding the subset with the highest combined affinity ranking in the respective portion; and
altering characteristics of the features surrounding the subset with the highest combined affinity ranking to reflect the optimal characteristics.